🧠 feat: Reasoning UI for Agents

[danny-avila]

Summary

• Configured the agent run process to assign a reasoningKey based on the endpoint
• Removed redundant debugging and commented-out code in the AgentClient to streamline logging.
• Enhanced formatAgentMessages and formatMessages to handle THINK-type (reasoning) content
• Integrated DeepSeek, and OpenRouter provider support and improved provider name normalization in initializeAgentOptions

Other Changes

• Improved error logging in OllamaClient by leveraging logAxiosError for clearer and less verbose API fetch failure details.
• Bumped dependency versions for https-proxy-agent to match @librechat/agents
• Added Proxy support for LC Code Interpreter API
• Typo in .env.example
• Default file config: add yml,yaml and log mimetype detection
• Google handle undefined family name

Checklist:

• My code adheres to this project's style guidelines
• I have performed a self-review of my own code
• I have commented in any complex areas of my code
• I have made pertinent documentation changes
• My changes do not introduce new warnings
• I have written tests demonstrating that my changes are effective or that my feature works
• Local unit tests pass with my changes
• Any changes dependent on mine have been merged and published in downstream modules